Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ada140ef452277a7387b9b9680e3f4f8b51ee018c06bea320aae6ff7dd56897
+oid sha256:7ca3c11975eb96f3debceff3fbdea962b02a219a99486e0814fb28177287659d
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083052ea7fe8c237bb03a4509fe6c3f1d59c871a4ec0b52ce03e86008b0cb179
+oid sha256:8447f4b6b1835c7330dbdb1a8bf0c8054e4afac283f9101f474b2bc25d38a00e
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3913b6d525fc41b598cb112c80bf2887de259a92d20c8c190a251ae3bec9b14f
+oid sha256:9a43eb41b34a48c5c14563c90af602cadf78e544704fba13476bf5335dd2d030
 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": 0.0011211809772960853,
+  "epoch": 0.0022423619545921705,
   "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": 352.69,
       "eval_steps_per_second": 176.502,
       "step": 3
+    },
+    {
+      "epoch": 0.0014949079697281135,
+      "grad_norm": 2.0927140712738037,
+      "learning_rate": 8e-05,
+      "loss": 44.4291,
+      "step": 4
+    },
+    {
+      "epoch": 0.001868634962160142,
+      "grad_norm": 1.9669666290283203,
+      "learning_rate": 0.0001,
+      "loss": 44.4457,
+      "step": 5
+    },
+    {
+      "epoch": 0.0022423619545921705,
+      "grad_norm": 2.133347749710083,
+      "learning_rate": 0.00012,
+      "loss": 44.4746,
+      "step": 6
+    },
+    {
+      "epoch": 0.0022423619545921705,
+      "eval_loss": 11.11185359954834,
+      "eval_runtime": 3.2602,
+      "eval_samples_per_second": 345.682,
+      "eval_steps_per_second": 172.994,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 36168007680.0,
+  "total_flos": 69924814848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null