Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2992684d1219f5d3069c8108ce240a1e473917cf46cb7aa62e06c5d9600073
+oid sha256:28f3aeebb1202728d8b105b97ea45d2e7343ff6780585f05976cc709ad028da3
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9b29f9cc888d00532f873a944e6b9fa61ab1097df14faafc0ce7fc2915668d
+oid sha256:ebd8e7dd7f52af0f9c6bdcf7d64980a6bdeb33ea4ead7b736d21184d0702c627
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62aa7846dcbf1dac4de2fc9a3f44f2d60deab35ce395ddd4c59a27a6bf2b0bed
+oid sha256:6ba58db7a4cd44d949f7914b684133d8cfddbc29710a68668016a0017331fb50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022944550669216062,
+  "epoch": 0.045889101338432124,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 60.437,
       "eval_steps_per_second": 30.768,
       "step": 3
+    },
+    {
+      "epoch": 0.030592734225621414,
+      "grad_norm": 29.1671085357666,
+      "learning_rate": 8e-05,
+      "loss": 11.1711,
+      "step": 4
+    },
+    {
+      "epoch": 0.03824091778202677,
+      "grad_norm": 15.751770973205566,
+      "learning_rate": 0.0001,
+      "loss": 9.6744,
+      "step": 5
+    },
+    {
+      "epoch": 0.045889101338432124,
+      "grad_norm": 18.53544807434082,
+      "learning_rate": 0.00012,
+      "loss": 11.195,
+      "step": 6
+    },
+    {
+      "epoch": 0.045889101338432124,
+      "eval_loss": 2.4405295848846436,
+      "eval_runtime": 1.0267,
+      "eval_samples_per_second": 53.572,
+      "eval_steps_per_second": 27.273,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89629692788736.0,
+  "total_flos": 179259385577472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null