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:a05aebaa7b015d89172d34eed489bb6a63c571bf9a1eb151f90dc9a56857dc55
+oid sha256:ec85568cb157d912833818d80fac2d9bafa714cd5e9cf4ea51b3d5d5c2a3d6ba
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6067ae1a8e1ad2f454b7793fa210d4803919a029e621f2b85a65b25bac975eb3
+oid sha256:db248925a0329a75eb24cc865850c9c1171b0fb63d6d3a0d4b23d86a6f5042a0
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbda33930318dcc51a6f38e3acb6a90f046b442ba380645e53c4907acf2ed1e
+oid sha256:746ada999513a3367ee104085c67b26fca950ad9cfcf6be9621f13d70a0c7a25
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05a68c0d6ab54c319b3d9db8dc84530b6a318b9993eda84ceffff913a62e005
+oid sha256:56c81d299a71b1a82f81e09cc8d1b4e6bd59d48b0b4bbb03c21769be189e6086
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e8869b7b250a20e25151837fa01074422f89f31d0236d56b1175bb1138aa0c
+oid sha256:134e761a8198187104ea8f981f72422d3157a25cf47b459cd23741acaf475a56
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7367d0b5b30030af66c3db85b8aa17e42f1640af2d258438fbaf2aa0630dc63
+oid sha256:aff32a51dbcc6f8f9adb857650126f318639c8a461cdf33fe7ea8df4e4d042b3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53322a9e0770f1aa889f3dc8eda417cbde627f634c75503b1e43849ff496ab
+oid sha256:d50872ebe2ae52bfb0e335aaa2e28a3dac724479a77b01ce7ef36e8156017c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9588377723970944,
+  "epoch": 3.0871670702179177,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,104 @@
       "eval_samples_per_second": 25.453,
       "eval_steps_per_second": 6.618,
       "step": 25
+    },
+    {
+      "epoch": 2.0581113801452786,
+      "grad_norm": 0.13160155713558197,
+      "learning_rate": 3.474083148320469e-05,
+      "loss": 0.2157,
+      "step": 26
+    },
+    {
+      "epoch": 2.135593220338983,
+      "grad_norm": 0.09340600669384003,
+      "learning_rate": 3.1406172239924584e-05,
+      "loss": 0.1305,
+      "step": 27
+    },
+    {
+      "epoch": 2.2130750605326877,
+      "grad_norm": 0.14144431054592133,
+      "learning_rate": 2.8241507066307104e-05,
+      "loss": 0.1193,
+      "step": 28
+    },
+    {
+      "epoch": 2.290556900726392,
+      "grad_norm": 0.0945616289973259,
+      "learning_rate": 2.5269637447446348e-05,
+      "loss": 0.1459,
+      "step": 29
+    },
+    {
+      "epoch": 2.3680387409200967,
+      "grad_norm": 0.09067712724208832,
+      "learning_rate": 2.2511975772046403e-05,
+      "loss": 0.1282,
+      "step": 30
+    },
+    {
+      "epoch": 2.4455205811138017,
+      "grad_norm": 0.1346789002418518,
+      "learning_rate": 1.9988391055670233e-05,
+      "loss": 0.1273,
+      "step": 31
+    },
+    {
+      "epoch": 2.523002421307506,
+      "grad_norm": 0.08553079515695572,
+      "learning_rate": 1.771706578402711e-05,
+      "loss": 0.2282,
+      "step": 32
+    },
+    {
+      "epoch": 2.6004842615012107,
+      "grad_norm": 0.08991867303848267,
+      "learning_rate": 1.5714364907746536e-05,
+      "loss": 0.124,
+      "step": 33
+    },
+    {
+      "epoch": 2.6779661016949152,
+      "grad_norm": 0.11215619742870331,
+      "learning_rate": 1.3994717932533891e-05,
+      "loss": 0.1235,
+      "step": 34
+    },
+    {
+      "epoch": 2.7554479418886197,
+      "grad_norm": 0.09423752874135971,
+      "learning_rate": 1.257051495425121e-05,
+      "loss": 0.1746,
+      "step": 35
+    },
+    {
+      "epoch": 2.8329297820823243,
+      "grad_norm": 0.10961948335170746,
+      "learning_rate": 1.1452017387992552e-05,
+      "loss": 0.1277,
+      "step": 36
+    },
+    {
+      "epoch": 2.910411622276029,
+      "grad_norm": 0.11356119066476822,
+      "learning_rate": 1.064728403435312e-05,
+      "loss": 0.1254,
+      "step": 37
+    },
+    {
+      "epoch": 3.009685230024213,
+      "grad_norm": 0.1418694704771042,
+      "learning_rate": 1.0162113015586309e-05,
+      "loss": 0.2462,
+      "step": 38
+    },
+    {
+      "epoch": 3.0871670702179177,
+      "grad_norm": 0.11329705268144608,
+      "learning_rate": 1e-05,
+      "loss": 0.1284,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -212,12 +310,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1215925807782298e+17,
+  "total_flos": 1.7496147569200333e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null