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:e09f7611a7d684d734bc45b72bbe9b8e0039f2f7ab4b98827d4be0ae98080037
+oid sha256:1b82d954557799a4ba7a600d6d4a39e0b40299d806699b1bbc453ed669131346
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5e117d37fdedea21f116fd388d0fa3d5183ad4201faa4df7a7de90dd1ebd5b
+oid sha256:d78541a2b29943e00f9fe49184fb1e0bf5f3b55288ee035f098e1034c9ae1aba
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2620fbeb73db5a9b150fdfc9afb93d77c631f09cbfd3caac798f467d8faea6d1
+oid sha256:e93b5bff3d43fe4c4fd31b8e38df5c260bc6b52a9ec8ea69ebecae13901b936d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020839121978327314,
+  "epoch": 0.027785495971103084,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 9.305,
       "eval_steps_per_second": 4.654,
       "step": 150
+    },
+    {
+      "epoch": 0.02222839677688247,
+      "grad_norm": 1.581220269203186,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 3.4549,
+      "step": 160
+    },
+    {
+      "epoch": 0.02361767157543762,
+      "grad_norm": 1.595863699913025,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 3.7633,
+      "step": 170
+    },
+    {
+      "epoch": 0.025006946373992776,
+      "grad_norm": 1.4789327383041382,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 3.6302,
+      "step": 180
+    },
+    {
+      "epoch": 0.02639622117254793,
+      "grad_norm": 1.2791557312011719,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 3.3965,
+      "step": 190
+    },
+    {
+      "epoch": 0.027785495971103084,
+      "grad_norm": 1.3027524948120117,
+      "learning_rate": 0.0,
+      "loss": 3.4079,
+      "step": 200
+    },
+    {
+      "epoch": 0.027785495971103084,
+      "eval_loss": 0.9190078377723694,
+      "eval_runtime": 325.7439,
+      "eval_samples_per_second": 9.305,
+      "eval_steps_per_second": 4.654,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.110810438664192e+16,
+  "total_flos": 1.2142470211043328e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null