Training in progress, step 200, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "unsloth/Qwen2-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151647
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151646,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf51944d7a4ee3b02dedfdc9ae3e19c0fabe5d72fa9de9e6d683c7732a10ba5
+size 3086579336

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296632ba00da4c7d578dbe8c4aa1c1b33d6ba698a81ffb8e2796543b493039f0
+size 3135948098

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2762d792d815ec78151cdfb1183ff8fe6b1a4c5fcc050ac87b15dc66050802
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc1f875219f8ac3c776408d86b647fbc8462ad7ecb23ac468a078c2c50ec46e
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcdba7bc63bee2e58552ca3df8d3d9521da29d066231bf49913479cc60a05a4
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac162cf8f57eb46f3e3f12f50328cd5574b5384b6fe27493b80f0979cc8d636b
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcd078b1186023c3032f4652f953246e76b5f62233ca3f894e881ea9feb17b7
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
+size 11418456

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.11111111111111,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": 2.402308225631714,
+      "eval_runtime": 19.0325,
+      "eval_samples_per_second": 78.865,
+      "eval_steps_per_second": 1.997,
+      "step": 1
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0001,
+      "loss": 2.0941,
+      "step": 10
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.8828125,
+      "learning_rate": 0.0002,
+      "loss": 1.9459,
+      "step": 20
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.000199658449300667,
+      "loss": 1.4091,
+      "step": 30
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 1.1276,
+      "step": 40
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 0.6824,
+      "step": 50
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 0.4638,
+      "step": 60
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.00019157733266550575,
+      "loss": 0.3579,
+      "step": 70
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.1979,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.00018371664782625287,
+      "loss": 0.1971,
+      "step": 90
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 0.1023,
+      "step": 100
+    },
+    {
+      "epoch": 6.111111111111111,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017357239106731317,
+      "loss": 0.1104,
+      "step": 110
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.0586,
+      "step": 120
+    },
+    {
+      "epoch": 7.222222222222222,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.0001614212712689668,
+      "loss": 0.0585,
+      "step": 130
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.025,
+      "step": 140
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 0.0184,
+      "step": 150
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0131,
+      "step": 160
+    },
+    {
+      "epoch": 9.444444444444445,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.00013246994692046836,
+      "loss": 0.0071,
+      "step": 170
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0043,
+      "step": 180
+    },
+    {
+      "epoch": 10.555555555555555,
+      "grad_norm": 0.23046875,
+      "learning_rate": 0.00011645945902807341,
+      "loss": 0.0025,
+      "step": 190
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0023,
+      "step": 200
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 3.9178080558776855,
+      "eval_runtime": 20.365,
+      "eval_samples_per_second": 73.705,
+      "eval_steps_per_second": 1.866,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 23,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2881172782645248e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bce95c2671e138389bee5812554e93e5a14ab975cbeaeec50391234e7a2ab3
+size 6904