Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43823720485b7c0b0a6002e378db7856e3f0cd4a663dff54b4c8ac57399ee23a
+oid sha256:a4aed5d87e199152659b25460199bacf1cbdb451de644a8d3a1f301e115f4139
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a215aba06725b96bf2c4035f6b1a36fc2a79ac5e7fe2dc9348d69a7f3588e407
+oid sha256:58c036578f6a651e990219d83c9f86366b958fd69a8be995972bcf61bfb9b982
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
+oid sha256:7393dbde4bffa4ea759a39a2e6dd5d0164b7e91c9e8ab3bfffc0ca38d5daac71
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
 size 627

last-checkpoint/tokenizer.json

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

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4440107345581055,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.6424810886383057,
+  "best_model_checkpoint": "./outputs/checkpoint-100",
+  "epoch": 0.07285974499089254,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,107 +11,23 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 2.7399,
+      "loss": 2.7401,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6418099403381348,
-      "eval_runtime": 347.6157,
-      "eval_samples_per_second": 18.049,
-      "eval_steps_per_second": 2.258,
+      "eval_loss": 2.6424810886383057,
+      "eval_runtime": 206.4108,
+      "eval_samples_per_second": 30.396,
+      "eval_steps_per_second": 3.803,
       "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
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.042513200078848e+16,
+  "total_flos": 2917794121482240.0,
   "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:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
+oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
 size 4219