Training in progress, step 256, checkpoint

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoint-64/logdata.jsonl filter=lfs diff=lfs merge=lfs -text
 checkpoint-128/logdata.jsonl filter=lfs diff=lfs merge=lfs -text
+checkpoint-256/logdata.jsonl filter=lfs diff=lfs merge=lfs -text

checkpoint-256/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bowphs/pythia-70m-multi",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

checkpoint-256/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.48.0.dev0"
+}

checkpoint-256/logdata.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbc4264e320003f39aef6c743f92dfb15fef8f28fc2a3cb2252ebeb7fc14297
+size 46388939

checkpoint-256/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d5bb2b38b1cb1fc0f4eba7d2bbdbc6b169257c346e8916a0b6246069d42067
+size 281715176

checkpoint-256/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e077df0087aecba82355c4fe0f5d53fbfede53c644817eceb68e5191ed9aa1
+size 563476858

checkpoint-256/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319eaf8fd01026c4190795a352f472cec2c7c84a8017bcf35b7317c2da9c97ce
+size 14244

checkpoint-256/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd076484d75c465b52d6c63bbcf10a2ad129c6e455197ed45ba31d5351656778
+size 1064

checkpoint-256/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-256/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-256/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.008533333333333334,
+  "eval_steps": 2000,
+  "global_step": 256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.3333333333333335e-05,
+      "eval_accuracy": 0.016437927663734114,
+      "eval_loss": 10.702861785888672,
+      "eval_runtime": 53.5239,
+      "eval_samples_per_second": 93.416,
+      "eval_steps_per_second": 2.933,
+      "step": 1
+    },
+    {
+      "epoch": 6.666666666666667e-05,
+      "eval_accuracy": 0.049564027370478984,
+      "eval_loss": 10.533119201660156,
+      "eval_runtime": 53.3666,
+      "eval_samples_per_second": 93.692,
+      "eval_steps_per_second": 2.942,
+      "step": 2
+    },
+    {
+      "epoch": 0.00013333333333333334,
+      "eval_accuracy": 0.05325317693059629,
+      "eval_loss": 10.302159309387207,
+      "eval_runtime": 53.3789,
+      "eval_samples_per_second": 93.67,
+      "eval_steps_per_second": 2.941,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002666666666666667,
+      "eval_accuracy": 0.053565591397849464,
+      "eval_loss": 10.023477554321289,
+      "eval_runtime": 53.6667,
+      "eval_samples_per_second": 93.168,
+      "eval_steps_per_second": 2.925,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005333333333333334,
+      "eval_accuracy": 0.06345063538611925,
+      "eval_loss": 9.653569221496582,
+      "eval_runtime": 53.2342,
+      "eval_samples_per_second": 93.925,
+      "eval_steps_per_second": 2.949,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010666666666666667,
+      "eval_accuracy": 0.07593020527859237,
+      "eval_loss": 9.028414726257324,
+      "eval_runtime": 53.4229,
+      "eval_samples_per_second": 93.593,
+      "eval_steps_per_second": 2.939,
+      "step": 32
+    },
+    {
+      "epoch": 0.0021333333333333334,
+      "eval_accuracy": 0.08323401759530792,
+      "eval_loss": 8.02489185333252,
+      "eval_runtime": 53.5928,
+      "eval_samples_per_second": 93.296,
+      "eval_steps_per_second": 2.929,
+      "step": 64
+    },
+    {
+      "epoch": 0.004266666666666667,
+      "eval_accuracy": 0.11289071358748778,
+      "eval_loss": 6.917232990264893,
+      "eval_runtime": 53.9308,
+      "eval_samples_per_second": 92.711,
+      "eval_steps_per_second": 2.911,
+      "step": 128
+    },
+    {
+      "epoch": 0.008533333333333334,
+      "eval_accuracy": 0.15581857282502443,
+      "eval_loss": 6.162940502166748,
+      "eval_runtime": 53.873,
+      "eval_samples_per_second": 92.811,
+      "eval_steps_per_second": 2.914,
+      "step": 256
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 30000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2248363839848448.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-256/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfb964096776c793ae319346657629d176228270098861d014f2f3c248437f7
+size 5304