Upload 12 files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566154a4dd8ca5ddf6cdf02c4ec1b80dd864ac6c9a268f2ce54b2aca0fa9cb95
+oid sha256:b45c7b495dc66a53e343991c9516e0d110bb2c061da4cec98096722e0f80f440
 size 903834408

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5861ce6f7a1779157da89556e25eacdf319ceee413c09009fd5a928f39524cc5
+size 1807824186

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b713008e4eea7860540db04296a11a09d44804872b072ac510cef9f0391ff3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61a714e2d67c35f405d9bbd18b18087fe1e54b1e2e331d14c8409a81e182f79
+size 1064

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.4945054945054945,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 52.2825,
+      "eval_gen_len": 17.3764,
+      "eval_loss": 0.2236185073852539,
+      "eval_meteor": 0.7138,
+      "eval_runtime": 20.1266,
+      "eval_samples_per_second": 26.135,
+      "eval_steps_per_second": 0.845,
+      "step": 91
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 58.1966,
+      "eval_gen_len": 17.3175,
+      "eval_loss": 0.1642024964094162,
+      "eval_meteor": 0.7742,
+      "eval_runtime": 15.2591,
+      "eval_samples_per_second": 34.471,
+      "eval_steps_per_second": 1.114,
+      "step": 182
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 62.8589,
+      "eval_gen_len": 17.6293,
+      "eval_loss": 0.15181176364421844,
+      "eval_meteor": 0.7831,
+      "eval_runtime": 15.3539,
+      "eval_samples_per_second": 34.258,
+      "eval_steps_per_second": 1.107,
+      "step": 273
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 64.9987,
+      "eval_gen_len": 17.5798,
+      "eval_loss": 0.14291420578956604,
+      "eval_meteor": 0.8085,
+      "eval_runtime": 15.3569,
+      "eval_samples_per_second": 34.252,
+      "eval_steps_per_second": 1.107,
+      "step": 364
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 65.7474,
+      "eval_gen_len": 17.5171,
+      "eval_loss": 0.13588279485702515,
+      "eval_meteor": 0.821,
+      "eval_runtime": 15.5893,
+      "eval_samples_per_second": 33.741,
+      "eval_steps_per_second": 1.09,
+      "step": 455
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 9.010989010989011e-06,
+      "loss": 0.2938,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1951729069178880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}