Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ded4bce8f3aeb46976eaf0b5329b44ad473a2a4305ab8d2f19270798882d91
+oid sha256:a9ab19a8a8f8fa395c8a765767034493cd40b33b06b69f316a5bc79f2fb8a137
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65835a5d88bd1313380b80afe6d10fa69949be4f94bd0e3624d1a7b2e009716
+oid sha256:f0b3b4462eee314e4809a24235151a982dab5d604d062fa3e99d0e2c7a7446c2
 size 60837186

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d62c754a4618e6e2045bed18fcd110ce3e033eadacd83db11e3e65d6fdb46b
+oid sha256:7fc69ab1dcca216771161e0b91f7d26d9c90fd7c25977be460383903db704a06
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4d68a8cd0d7c336eae5ec9326f4344f8484e56ac5abb9db3c35753732b9e85
+oid sha256:975fb42b56b65e8821d845db3ce30cfc648ea90ad5ce64077e43a4d086f034fc
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814cb1a0cec135cba6a03f6f7a188e85ada15f60bf1b79a649c42e89652b64a2
+oid sha256:d61d85a65f01744d9a673e2b200c99e2454febba890b00c501a234f6e9909e25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5059288537549407,
+  "epoch": 0.758893280632411,
   "eval_steps": 16,
-  "global_step": 32,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -255,6 +255,126 @@
       "eval_samples_per_second": 12.972,
       "eval_steps_per_second": 3.273,
       "step": 32
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.6524657011032104,
+      "learning_rate": 6.6e-05,
+      "loss": 0.1999,
+      "step": 33
+    },
+    {
+      "epoch": 0.5375494071146245,
+      "grad_norm": 1.1696100234985352,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.3284,
+      "step": 34
+    },
+    {
+      "epoch": 0.5533596837944664,
+      "grad_norm": 0.16617901623249054,
+      "learning_rate": 7e-05,
+      "loss": 0.0075,
+      "step": 35
+    },
+    {
+      "epoch": 0.5691699604743083,
+      "grad_norm": 0.34399452805519104,
+      "learning_rate": 7.2e-05,
+      "loss": 0.0108,
+      "step": 36
+    },
+    {
+      "epoch": 0.5849802371541502,
+      "grad_norm": 0.39466115832328796,
+      "learning_rate": 7.4e-05,
+      "loss": 0.0283,
+      "step": 37
+    },
+    {
+      "epoch": 0.6007905138339921,
+      "grad_norm": 0.31488093733787537,
+      "learning_rate": 7.6e-05,
+      "loss": 0.0178,
+      "step": 38
+    },
+    {
+      "epoch": 0.616600790513834,
+      "grad_norm": 0.32184290885925293,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.011,
+      "step": 39
+    },
+    {
+      "epoch": 0.6324110671936759,
+      "grad_norm": 0.395563006401062,
+      "learning_rate": 8e-05,
+      "loss": 0.0096,
+      "step": 40
+    },
+    {
+      "epoch": 0.6482213438735178,
+      "grad_norm": 0.22120489180088043,
+      "learning_rate": 8.2e-05,
+      "loss": 0.005,
+      "step": 41
+    },
+    {
+      "epoch": 0.6640316205533597,
+      "grad_norm": 0.3320792317390442,
+      "learning_rate": 8.4e-05,
+      "loss": 0.008,
+      "step": 42
+    },
+    {
+      "epoch": 0.6798418972332015,
+      "grad_norm": 0.28633660078048706,
+      "learning_rate": 8.6e-05,
+      "loss": 0.005,
+      "step": 43
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.4111138582229614,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.0084,
+      "step": 44
+    },
+    {
+      "epoch": 0.7114624505928854,
+      "grad_norm": 0.06865093857049942,
+      "learning_rate": 9e-05,
+      "loss": 0.0019,
+      "step": 45
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.05319277197122574,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.0016,
+      "step": 46
+    },
+    {
+      "epoch": 0.7430830039525692,
+      "grad_norm": 0.6792236566543579,
+      "learning_rate": 9.4e-05,
+      "loss": 0.1265,
+      "step": 47
+    },
+    {
+      "epoch": 0.758893280632411,
+      "grad_norm": 0.5738235712051392,
+      "learning_rate": 9.6e-05,
+      "loss": 0.0992,
+      "step": 48
+    },
+    {
+      "epoch": 0.758893280632411,
+      "eval_loss": 0.025439240038394928,
+      "eval_runtime": 8.0993,
+      "eval_samples_per_second": 13.211,
+      "eval_steps_per_second": 3.334,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -274,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4791247562604544.0,
+  "total_flos": 7214050224111616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null