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:c2cb0d78df94c0e2dd90b799414771e0df80371c32d670ad388edb8b1c86decd
+oid sha256:bd42e64a404c92e8c5032da404e7485de60e7cf942fd82603d31ff987aa8169c
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9427ee619d280d2aecb6e178af800bb63d400db5f6a2d5f58ba7f6817b91a37a
+oid sha256:c4ea092e927449abca260966bf3af8be88cdbdcfe14ecbbdea5f058050d721e8
 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": 0.011933174224343675,
+  "epoch": 0.02386634844868735,
   "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": 0.7825,
       "step": 5
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "grad_norm": 1.0612146854400635,
+      "learning_rate": 0.00012,
+      "loss": 0.8894,
+      "step": 6
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "eval_loss": 0.9630873799324036,
+      "eval_runtime": 27.2494,
+      "eval_samples_per_second": 6.496,
+      "eval_steps_per_second": 3.266,
+      "step": 6
+    },
+    {
+      "epoch": 0.016706443914081145,
+      "grad_norm": 0.7056834101676941,
+      "learning_rate": 0.00014,
+      "loss": 0.8648,
+      "step": 7
+    },
+    {
+      "epoch": 0.01909307875894988,
+      "grad_norm": 0.8485152125358582,
+      "learning_rate": 0.00016,
+      "loss": 1.0942,
+      "step": 8
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "grad_norm": 0.4888964891433716,
+      "learning_rate": 0.00018,
+      "loss": 0.7532,
+      "step": 9
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "eval_loss": 0.9085158109664917,
+      "eval_runtime": 27.2896,
+      "eval_samples_per_second": 6.486,
+      "eval_steps_per_second": 3.261,
+      "step": 9
+    },
+    {
+      "epoch": 0.02386634844868735,
+      "grad_norm": 0.5342348217964172,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "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