Upload . with huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00356c4ec79b7c77d561ecaab1a6c680ef6bf274ce641cd570e935d52cc86fe4
+size 4473880501

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99626a59946fbcb9fad13ee1029e247697cafaf54a0c262af62314aeed3f79b6
+size 2236953377

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17fa06ae763635fe0359eb08c545c3b7f89e80fc0247a7b24b8a77e4708bd61
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12990764445c4d92cd3ecd547746aeb2443381908df99441dc8d7da081f15b8
+size 627

trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.142857142857143,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.3697612285614014,
+      "eval_runtime": 53.7583,
+      "eval_samples_per_second": 4.874,
+      "eval_steps_per_second": 0.614,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.350198745727539,
+      "eval_runtime": 52.6608,
+      "eval_samples_per_second": 4.975,
+      "eval_steps_per_second": 0.627,
+      "step": 280
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.6000664234161377,
+      "eval_runtime": 51.3966,
+      "eval_samples_per_second": 5.098,
+      "eval_steps_per_second": 0.642,
+      "step": 420
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 1.8394,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.011274576187134,
+      "eval_runtime": 51.1881,
+      "eval_samples_per_second": 5.118,
+      "eval_steps_per_second": 0.645,
+      "step": 560
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.5172500610351562,
+      "eval_runtime": 53.2278,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 0.62,
+      "step": 700
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.840390682220459,
+      "eval_runtime": 53.3892,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 0.618,
+      "step": 840
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.020865440368652,
+      "eval_runtime": 52.1972,
+      "eval_samples_per_second": 5.019,
+      "eval_steps_per_second": 0.632,
+      "step": 980
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.4408,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1400,
+  "num_train_epochs": 10,
+  "total_flos": 1857413971968000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ac49390de10588789eb996968293eaf1dabcacab3d598975996a668bbec820
+size 3387