Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c4392b09dcaeb6c5c8bf220652aee3d323959002e8ffe728c029579d87322f
+oid sha256:650cec4efaa6e5c89a9398d8984e5217b9438019cd88213a42bc36a3134da02c
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec84c0c491e4300d8f072b270a3ea58446fa0c6e6333b5bd49c3f4585e020c5f
+oid sha256:28541c2260545c0e45c60e2679351f034deec590ea2617483eb6506671c72d6a
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24df05627e2e86925ca37683e21f902381144a8ad40105a0738461c44ce5f2e2
+oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008150291372916582,
+  "epoch": 0.0016300582745833164,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 1.256,
       "step": 5
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "grad_norm": 1.1818934679031372,
+      "learning_rate": 0.00012,
+      "loss": 1.7772,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "eval_loss": 1.5226942300796509,
+      "eval_runtime": 374.5727,
+      "eval_samples_per_second": 6.896,
+      "eval_steps_per_second": 3.449,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011410407922083214,
+      "grad_norm": 1.2571606636047363,
+      "learning_rate": 0.00014,
+      "loss": 1.5778,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013040466196666532,
+      "grad_norm": 3.4298977851867676,
+      "learning_rate": 0.00016,
+      "loss": 2.0878,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "grad_norm": 0.920394241809845,
+      "learning_rate": 0.00018,
+      "loss": 1.583,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "eval_loss": 1.4455409049987793,
+      "eval_runtime": 373.3626,
+      "eval_samples_per_second": 6.918,
+      "eval_steps_per_second": 3.46,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016300582745833164,
+      "grad_norm": 0.9525576233863831,
+      "learning_rate": 0.0002,
+      "loss": 1.2694,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null