Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1cbf07201e2361e23941adedcf0939ac84b301fe9e042c17d6b0ccacc571ddb
+oid sha256:dc896d9a31fec3347a78d31be4fe1f49ec14e369415b658503f001b1d84fe338
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ecaf9d269566bb9b48724a3d823010a908c988a4344d2e6a7e698410e137629
+oid sha256:a96c0758b611fa4347bbfb780c5819105b2f37539ea6bd069a25f799125a5e12
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4281edb305ff2732d6945c705f7f8f1964c308bbc59a1ec5d26a1f2a7663c750
+oid sha256:54fbaba1ddfebd4b89dec166b252d6079eab8ffb812f4b0f72ec2d9a57e46917
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2455021142959595,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.2179733514785767,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 10.699,
       "eval_steps_per_second": 1.342,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0213,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.2179733514785767,
+      "eval_runtime": 177.6597,
+      "eval_samples_per_second": 10.863,
+      "eval_steps_per_second": 1.362,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7473455614033920.0,
+  "total_flos": 1.492559003271168e+16,
   "trial_name": null,
   "trial_params": null
 }