Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277a1171319ef648c8b3343278646f15581f585f98229d608df0ebca53641c62
+oid sha256:f18028fc41afdf833024213b54fbbc1f1dac2f3160ee1aa10f29a0e2e24496e1
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66766fed26e5b03af3ddbf7f30bf9ad40609a3e84bdde3047a65d01d7505f674
+oid sha256:d9d691fb0e9998f666b2927dc326dd544d7d7c2754aeeff473b97413a1edbb11
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f388398ea994e40704f6497243bd60adc9aa3f265cb5542e356410fda11e77
+oid sha256:4362fcd5a37a292cbf977b943f0b3f947ac977ee861d18729b9f450b9c75768d
 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": 1.2689,
       "step": 5
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "grad_norm": 0.7671542763710022,
+      "learning_rate": 0.00012,
+      "loss": 1.6685,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "eval_loss": 1.4657011032104492,
+      "eval_runtime": 788.5529,
+      "eval_samples_per_second": 3.276,
+      "eval_steps_per_second": 1.638,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011410407922083214,
+      "grad_norm": 0.8560234308242798,
+      "learning_rate": 0.00014,
+      "loss": 1.5098,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013040466196666532,
+      "grad_norm": 3.3206217288970947,
+      "learning_rate": 0.00016,
+      "loss": 2.1037,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "grad_norm": 0.6197188496589661,
+      "learning_rate": 0.00018,
+      "loss": 1.4734,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "eval_loss": 1.3432879447937012,
+      "eval_runtime": 788.8077,
+      "eval_samples_per_second": 3.275,
+      "eval_steps_per_second": 1.638,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016300582745833164,
+      "grad_norm": 0.623649537563324,
+      "learning_rate": 0.0002,
+      "loss": 1.1344,
+      "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": 2794842929233920.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null