Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe631d2abad406695e6d180dced2bde0902c868474b8d2c4f36de4cadffd9e48
+oid sha256:2adc63d86867e32465a08e11669c0a4e78070b9fa85d80367570bde7d84dacf2
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798c2ae1e6dff48072797de0adcb6823ce7a7fdbddb5d729b451780944ef9ef4
+oid sha256:d66bb8cca73946291d31c3520cba26cfb1869a9b08802c3706ee0d79b7a5ea58
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da1280f00d05c94b786e42e947c1fdef9fa41c2297c39831ded2e8566dc003e
+oid sha256:be9ec3198a68ec65f16686b0f1d5a6ba174d2aca875621b68207c99c69128ae9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963abeacc51d2fd967b0d854376103780952d47675257465be60a3612cecb103
+oid sha256:416d32fdf638b555a0fc031fb149fd18abaec9c234026f168a4a4bd45704a2a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08313466593312549,
+  "epoch": 0.08557980316645272,
   "eval_steps": 34,
-  "global_step": 170,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1245,6 +1245,41 @@
       "eval_samples_per_second": 2.933,
       "eval_steps_per_second": 0.978,
       "step": 170
+    },
+    {
+      "epoch": 0.08362369337979095,
+      "grad_norm": Infinity,
+      "learning_rate": 1.4020014855162755e-05,
+      "loss": 8.3255,
+      "step": 171
+    },
+    {
+      "epoch": 0.08411272082645639,
+      "grad_norm": Infinity,
+      "learning_rate": 1.3091105369447165e-05,
+      "loss": 9.7255,
+      "step": 172
+    },
+    {
+      "epoch": 0.08460174827312184,
+      "grad_norm": 7.069207206448595e+18,
+      "learning_rate": 1.2191875191630209e-05,
+      "loss": 9.0893,
+      "step": 173
+    },
+    {
+      "epoch": 0.08509077571978728,
+      "grad_norm": Infinity,
+      "learning_rate": 1.1322631407993811e-05,
+      "loss": 9.1109,
+      "step": 174
+    },
+    {
+      "epoch": 0.08557980316645272,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0483670864493778e-05,
+      "loss": 10.0142,
+      "step": 175
     }
   ],
   "logging_steps": 1,
@@ -1264,7 +1299,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.7476154491273216e+17,
+  "total_flos": 3.857839432925184e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null