Training in progress, step 40, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "katuni4ka/tiny-random-qwen1.5-moe",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 22,
+  "max_position_embeddings": 2048,
+  "max_window_layers": 2,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 44,
+  "norm_topk_prob": false,
+  "num_attention_heads": 4,
+  "num_experts": 8,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 22,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1ab77025bc13ba8fd3a3ab33e66cd3d3895d274cfd19f5984b2f7fd28ebd37
+size 19745440

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1732af4087baee42ae033819410e1e99af4ef26905cae47af0aa978accae2e71
+size 21069498

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df10be429c2412198f2c4c684866a8c921cbd0d9ee4c865077476da07bda410
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14d8363b71c1e824421bf14a513f0f951f1c6c9b9494dcedc75b3fa1fecea91
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d27a8e9aed69fdd3b729f8cbf6300af5e0e26e9226d0e2307b0cf80aff9030
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23de9e35ad029c7a59ff383920fe892474d8f295c2e2f82ec3e6f109f3f96960
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50724f43561b5c511c4e37bb1b8ec7e620ff22332c4f39576452e56a9e02d18d
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8d108db37b78249e3b0beb22f6120e06fd369dd9fbaa19526994e040db5f9d
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e62597393912992a3de2b36aa1663274b75b96f6525f5504e64377c5049c51e
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1f0a5c61bcbceb46a2a335e00a59c951081a94126a8ae4cc9a9102e012eb65
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea54818dbc15bd81d4941b71d5e2806c555d1a733f768c00c5f1a670e0a08fb1
+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": "<|endoftext|>",
+    "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:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.047337278106508875,
+  "eval_steps": 20,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001183431952662722,
+      "eval_loss": 11.93152904510498,
+      "eval_runtime": 4.3808,
+      "eval_samples_per_second": 342.861,
+      "eval_steps_per_second": 21.457,
+      "step": 1
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 0.5202497839927673,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 11.9327,
+      "step": 10
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 0.41039279103279114,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 11.9349,
+      "step": 20
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "eval_loss": 11.930181503295898,
+      "eval_runtime": 4.2798,
+      "eval_samples_per_second": 350.949,
+      "eval_steps_per_second": 21.963,
+      "step": 20
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 0.6066334247589111,
+      "learning_rate": 4.8e-05,
+      "loss": 11.9306,
+      "step": 30
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 0.46611225605010986,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 11.9262,
+      "step": 40
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "eval_loss": 11.922493934631348,
+      "eval_runtime": 4.3258,
+      "eval_samples_per_second": 347.218,
+      "eval_steps_per_second": 21.73,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 39525514477568.0,
+  "train_batch_size": 2,
+  "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:b925c4aa24e9ed00a85109bf16795e4125cfa4c22e502965ecc2e11808027d4b
+size 6840