Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6786a7e41ebfcfd9932b459935a215f8ebec4f7b7d4b51c05869e30aff97a40
+oid sha256:dd60c41843428e1b79d82ed5e8a6ca5a63df384a3d4ae70610ab91e9d7622128
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03b074570a0ff3a9c1a1337dceb1382505c03a5c0e313013a67abe37e5618db
+oid sha256:4022a9ac3c7308cd04fc492323d56144cd4d417816030f86fd2ff356f1b6a85d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7393dbde4bffa4ea759a39a2e6dd5d0164b7e91c9e8ab3bfffc0ca38d5daac71
+oid sha256:4cf66005e5e6a4f3553669f4e9894b69e1bc5f9207c5bf2c3d2ce3aab9394607
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
+size 14500569

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6424405574798584,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.07285974499089254,
+  "best_metric": 2.4231719970703125,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,23 +11,121 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 2.7406,
+      "loss": 2.7399,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6424405574798584,
-      "eval_runtime": 206.8728,
-      "eval_samples_per_second": 30.328,
-      "eval_steps_per_second": 3.795,
+      "eval_loss": 2.6418099403381348,
+      "eval_runtime": 347.6157,
+      "eval_samples_per_second": 18.049,
+      "eval_steps_per_second": 2.258,
       "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 2.6052,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 2.5918312072753906,
+      "eval_runtime": 333.731,
+      "eval_samples_per_second": 18.8,
+      "eval_steps_per_second": 2.352,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.5622,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.551574468612671,
+      "eval_runtime": 204.9306,
+      "eval_samples_per_second": 30.615,
+      "eval_steps_per_second": 3.831,
+      "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 2.5366,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.517575263977051,
+      "eval_runtime": 204.3925,
+      "eval_samples_per_second": 30.696,
+      "eval_steps_per_second": 3.841,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.4946,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.4924821853637695,
+      "eval_runtime": 204.4035,
+      "eval_samples_per_second": 30.694,
+      "eval_steps_per_second": 3.84,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 2.4686,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 2.4666266441345215,
+      "eval_runtime": 207.3453,
+      "eval_samples_per_second": 30.259,
+      "eval_steps_per_second": 3.786,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.4503,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.4440107345581055,
+      "eval_runtime": 205.5485,
+      "eval_samples_per_second": 30.523,
+      "eval_steps_per_second": 3.819,
+      "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.4271,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.4231719970703125,
+      "eval_runtime": 204.3763,
+      "eval_samples_per_second": 30.698,
+      "eval_steps_per_second": 3.841,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2917794121482240.0,
+  "total_flos": 2.333865205776384e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bbb4e93666410d7a938dd3851f7194e97be075889249a5ac42f4cb3cfacdd3
+oid sha256:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
 size 4219