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:cb883655aa426c79b369ab0a4e4c3f54606818d9b48d26a186a4d8960804f840
+oid sha256:8f66355456c2b6363117639866b0e5d7724ee49d08c14cfe54ff099969335518
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaee067fe18c9ff6b75dd94d66dc56422f27c22cf10e4b3d9fbf33c745de600b
+oid sha256:de9b75d7ad751e5e2cfba8a6fd408d45f5001218c732e143401682f409c9590a
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1ed5ef878d1cb5694ce6c44d444574299065f1806fd6b37cb49af7d452c98c
+oid sha256:87b368c128ea0a3e3249112be27647c1e5cf6b066033174cae0f792ccb2e0084
 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": 0.00014325108333631772,
+  "epoch": 0.00028650216667263544,
   "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": 0.9949,
       "step": 5
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "grad_norm": 0.9874056577682495,
+      "learning_rate": 0.00012,
+      "loss": 0.8694,
+      "step": 6
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "eval_loss": 0.9844986200332642,
+      "eval_runtime": 201.5424,
+      "eval_samples_per_second": 72.923,
+      "eval_steps_per_second": 36.464,
+      "step": 6
+    },
+    {
+      "epoch": 0.00020055151667084482,
+      "grad_norm": 1.2436754703521729,
+      "learning_rate": 0.00014,
+      "loss": 0.7273,
+      "step": 7
+    },
+    {
+      "epoch": 0.00022920173333810837,
+      "grad_norm": 0.8379012942314148,
+      "learning_rate": 0.00016,
+      "loss": 0.9509,
+      "step": 8
+    },
+    {
+      "epoch": 0.0002578519500053719,
+      "grad_norm": 0.9932730197906494,
+      "learning_rate": 0.00018,
+      "loss": 0.8936,
+      "step": 9
+    },
+    {
+      "epoch": 0.0002578519500053719,
+      "eval_loss": 0.9006158113479614,
+      "eval_runtime": 213.2771,
+      "eval_samples_per_second": 68.91,
+      "eval_steps_per_second": 34.458,
+      "step": 9
+    },
+    {
+      "epoch": 0.00028650216667263544,
+      "grad_norm": 0.7014549374580383,
+      "learning_rate": 0.0002,
+      "loss": 0.9925,
+      "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": 34292650475520.0,
+  "total_flos": 68585300951040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null