Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdc3d4f08838b4110ecdcba206e9a963839b476e78f3ec016e8ece82271095e
+oid sha256:e9ab32ec8f81b455b9a5e62cb6615269b2a7107e305c7509f50cf851dba291d1
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e79619f3a1864e0d4629885c0a433d87efe4b4b533e5819cdc4a15efe1e097f
+oid sha256:eb77724ea41b6e9f9516013e317616d8782970a3ff6655065b5d2cc7a58f74f3
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c96b5e6811e264a82636893b20993c7fd3b70e662b81fe25e9b6d360eb6062
+oid sha256:400a6d6a18fc16b638aeb824699e8e27e212104bd39097badfed36b500f6402a
 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": 0.004748713889988128,
+  "epoch": 0.009497427779976256,
   "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": 56.821,
       "eval_steps_per_second": 28.517,
       "step": 3
+    },
+    {
+      "epoch": 0.006331618519984171,
+      "grad_norm": 1.1604503393173218,
+      "learning_rate": 8e-05,
+      "loss": 10.0903,
+      "step": 4
+    },
+    {
+      "epoch": 0.007914523149980214,
+      "grad_norm": 1.1817126274108887,
+      "learning_rate": 0.0001,
+      "loss": 11.4336,
+      "step": 5
+    },
+    {
+      "epoch": 0.009497427779976256,
+      "grad_norm": 1.3432368040084839,
+      "learning_rate": 0.00012,
+      "loss": 10.6907,
+      "step": 6
+    },
+    {
+      "epoch": 0.009497427779976256,
+      "eval_loss": 2.689335584640503,
+      "eval_runtime": 4.7614,
+      "eval_samples_per_second": 56.076,
+      "eval_steps_per_second": 28.143,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89618821152768.0,
+  "total_flos": 179237642305536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null