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:e0c79a8915186973249b94855c88602159d4856699d6050f5ba73e7f759979c3
+oid sha256:56702f5b12d2a701e109e8b9dfd9424d22cbccfad425c263040fff5c9b688777
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5873f0c2343b8e5f4d9cc234f1749b6ba66b331c1483dab364c6310b3ef3422a
+oid sha256:a50dcb6020213e50bad0435ed00d7d05302b00357a6bbbb420e721c750851123
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd197233abf432c0c23452d37e2c9eac62609b8e7d27929b13fe5bd30a4bf41
+oid sha256:27d776c8cc8c19ee4cf945ef22e749c46eac2116aa5a9db2f8ab1fcc9c5a3069
 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": 0.00013823610727121925,
+  "epoch": 0.0002764722145424385,
   "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": 12.001,
       "eval_steps_per_second": 6.0,
       "step": 3
+    },
+    {
+      "epoch": 0.000184314809694959,
+      "grad_norm": 0.29292038083076477,
+      "learning_rate": 8e-05,
+      "loss": 3.0989,
+      "step": 4
+    },
+    {
+      "epoch": 0.00023039351211869873,
+      "grad_norm": 0.3303835690021515,
+      "learning_rate": 0.0001,
+      "loss": 3.9467,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002764722145424385,
+      "grad_norm": 0.40217289328575134,
+      "learning_rate": 0.00012,
+      "loss": 4.5857,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002764722145424385,
+      "eval_loss": 1.1704449653625488,
+      "eval_runtime": 981.3093,
+      "eval_samples_per_second": 9.312,
+      "eval_steps_per_second": 4.656,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1662267760312320.0,
+  "total_flos": 3245379912990720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null