Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c57fe09243896e76e6f76c61f17bc3984147f179fca4fb74f9ffa39488fe0c0
+oid sha256:775d50206878581dfe06ec2396904f1d59c23c680396c2cd1f3525cccb567480
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfdbc7bca82335aae340b66c7faa043a100ef8deb0953fa142d1c1c8131445d
+oid sha256:0c2aa9216e4e1a07f85db34440ac81d831b797ceb306ad4cdc207f086df04e93
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfadc05d2d983979ebf39752461dcf62eb230eb8d820bd09cf23d7888d9df570
+oid sha256:2f3771cff6451a6af8ba56cd60be1bd6705dffa64cc52c8fdd9f27e3f1d0b72f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826ab5cbdeebfceff791289dbda0e94c2a0531ba16021b3dca9d34da57cc673a
+oid sha256:5ae10977704005c7d5bcd9df9eff952d9a1d3f45b6f2413e502030767ab97045
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4f8bcc2f798ba5b1e1d3cd63c141ee8b120ed84e3abbab7c93fa5dd43e4059
+oid sha256:7e78d5e09340c0681df725fbe1595e157ca67a75816fc394229ff49b11a9add2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7862407862407862,
+  "epoch": 1.0221130221130221,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,69 @@
       "eval_samples_per_second": 37.045,
       "eval_steps_per_second": 9.369,
       "step": 30
+    },
+    {
+      "epoch": 0.8124488124488124,
+      "grad_norm": 0.4604407548904419,
+      "learning_rate": 1.1098212284078036e-05,
+      "loss": 1.6154,
+      "step": 31
+    },
+    {
+      "epoch": 0.8386568386568387,
+      "grad_norm": 0.4262702763080597,
+      "learning_rate": 8.574517537807897e-06,
+      "loss": 1.6072,
+      "step": 32
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.452141135931015,
+      "learning_rate": 6.349294341940593e-06,
+      "loss": 1.6484,
+      "step": 33
+    },
+    {
+      "epoch": 0.8910728910728911,
+      "grad_norm": 0.45040103793144226,
+      "learning_rate": 4.43857548059321e-06,
+      "loss": 1.6131,
+      "step": 34
+    },
+    {
+      "epoch": 0.9172809172809173,
+      "grad_norm": 0.43721693754196167,
+      "learning_rate": 2.85612772694579e-06,
+      "loss": 1.5875,
+      "step": 35
+    },
+    {
+      "epoch": 0.9434889434889435,
+      "grad_norm": 0.4300181269645691,
+      "learning_rate": 1.6133526533250565e-06,
+      "loss": 1.6122,
+      "step": 36
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.4537125825881958,
+      "learning_rate": 7.192044826145771e-07,
+      "loss": 1.6159,
+      "step": 37
+    },
+    {
+      "epoch": 0.9959049959049959,
+      "grad_norm": 0.44113290309906006,
+      "learning_rate": 1.8012557287367392e-07,
+      "loss": 1.6142,
+      "step": 38
+    },
+    {
+      "epoch": 1.0221130221130221,
+      "grad_norm": 1.147554636001587,
+      "learning_rate": 0.0,
+      "loss": 2.9159,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -263,12 +326,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.425617760446054e+16,
+  "total_flos": 1.2251367690416947e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null