Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e6b3e1d595414a7d7c782b65a9be536e02782b01c4d1af44ba2aceb43834f0
+oid sha256:d44bc5be1e3118d2e77ce82df05169f0d9aabeb7f36133abc9476b7e106edf50
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c6db5f642cc4524ca1d733bd074dee4ddbfa7832cd101cbbb5fb6b5db1d572
+oid sha256:9d59946c8391924c55bdbeee729207f19b6103e226220bb310247dcc3cc9d9cb
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878afb72930bbe35f3f76161250c8b6ec3eee322b00164ea89731e27a1aeb55c
+oid sha256:e89a5182bb97955f9b45a8cc3c3bf35765c6a725efad38ec6b58f6ba203942c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b978c4f5387d059752764238c4bee9571cf3df7a5c984a19baed3fed0a46071c
+oid sha256:dac856699362054adec05f5effdce5ef83a8d5422ff5e800f6e464aadfae0e0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0865800865800868,
+  "epoch": 2.346320346320346,
   "eval_steps": 15,
-  "global_step": 120,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 4.437,
       "eval_steps_per_second": 0.595,
       "step": 120
+    },
+    {
+      "epoch": 2.1385281385281387,
+      "grad_norm": 1.176239252090454,
+      "learning_rate": 2.1474873544905205e-05,
+      "loss": 1.7413,
+      "step": 123
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 1.239511489868164,
+      "learning_rate": 1.914947017978153e-05,
+      "loss": 1.8036,
+      "step": 126
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 1.0849404335021973,
+      "learning_rate": 1.692717868719195e-05,
+      "loss": 1.9443,
+      "step": 129
+    },
+    {
+      "epoch": 2.2943722943722946,
+      "grad_norm": 1.1872035264968872,
+      "learning_rate": 1.4815426642560754e-05,
+      "loss": 1.7633,
+      "step": 132
+    },
+    {
+      "epoch": 2.346320346320346,
+      "grad_norm": 1.1865441799163818,
+      "learning_rate": 1.2821272164789544e-05,
+      "loss": 1.8487,
+      "step": 135
+    },
+    {
+      "epoch": 2.346320346320346,
+      "eval_loss": 0.6821556687355042,
+      "eval_runtime": 21.8619,
+      "eval_samples_per_second": 4.437,
+      "eval_steps_per_second": 0.595,
+      "step": 135
     }
   ],
   "logging_steps": 3,
@@ -378,7 +421,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.169594538911334e+17,
+  "total_flos": 6.94240387572695e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null