Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db5ff79722031db7d9a48215670b7ccf3322b63c332d79c11d9d57f556a4ed9
+oid sha256:740e0dc2f40f0448bc63e7af7168d7aa3e298441a437bf5c615c648d0e17771c
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f309cd81061d2239760265589e8da67714ac1967effbdfe604a5e93a49a7c2db
+oid sha256:ddf8f5c08ff37f7375fa2c8806253f46be1f4a35fdfb86e59ab100a8c253ed06
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b4f18465ce9ef7259d4d32c3f46950866de434ba10601e538309c0f6351e0d
+oid sha256:dba86a6be2e6de4dc2658b46fbfd882bdc9346ad7ae3a64beb5b38471d54c4b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2a6301db2b5e58d7c810f9f0f35dee18c800d0cef729c658d7f5a962d36075
+oid sha256:73773cdbadae7579ea0445987a6ef1cd08a6a2924f2d011103f0b5b3efe812b5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0026258205689276,
+  "epoch": 2.1006564551422318,
   "eval_steps": 50,
-  "global_step": 143,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1032,6 +1032,63 @@
       "learning_rate": 1.0705439301261887e-06,
       "loss": 0.9681,
       "step": 143
+    },
+    {
+      "epoch": 2.0166301969365428,
+      "grad_norm": 2.1956636905670166,
+      "learning_rate": 7.870200411711658e-07,
+      "loss": 0.97,
+      "step": 144
+    },
+    {
+      "epoch": 2.0306345733041575,
+      "grad_norm": 2.438053607940674,
+      "learning_rate": 5.46834442645952e-07,
+      "loss": 0.9683,
+      "step": 145
+    },
+    {
+      "epoch": 2.0446389496717723,
+      "grad_norm": 4.763875484466553,
+      "learning_rate": 3.501273961763529e-07,
+      "loss": 1.1133,
+      "step": 146
+    },
+    {
+      "epoch": 2.0586433260393875,
+      "grad_norm": 1.9470134973526,
+      "learning_rate": 1.9701377313817158e-07,
+      "loss": 0.6127,
+      "step": 147
+    },
+    {
+      "epoch": 2.0726477024070022,
+      "grad_norm": 2.1176681518554688,
+      "learning_rate": 8.758298757550186e-08,
+      "loss": 0.9606,
+      "step": 148
+    },
+    {
+      "epoch": 2.086652078774617,
+      "grad_norm": 2.0052874088287354,
+      "learning_rate": 2.1898943985529384e-08,
+      "loss": 0.6702,
+      "step": 149
+    },
+    {
+      "epoch": 2.1006564551422318,
+      "grad_norm": 1.8249067068099976,
+      "learning_rate": 0.0,
+      "loss": 0.4741,
+      "step": 150
+    },
+    {
+      "epoch": 2.1006564551422318,
+      "eval_loss": 0.03468266502022743,
+      "eval_runtime": 37.372,
+      "eval_samples_per_second": 6.449,
+      "eval_steps_per_second": 3.238,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -1046,12 +1103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.45942200188928e+18,
+  "total_flos": 1.530862239744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null