Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8526645aa10c8c370c36943130d1cefbfc8f02dbcdbe98fd4c9bd8b917e57f
+oid sha256:4e326cab99b9185673026663619315b66fbc144ff1c4a4cc0f73758d0a7e97df
 size 1579384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21615e5cb8507075c0003e1546245cfedd277c9465b3b44f7587a57f804e30af
+oid sha256:acb1b63fea4a66c08312e4978f73870c35ab3335f4b1705b84dcf6d655978dc5
 size 857274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eff25987b5fd2c04395d3be2d6b618db1a3880a66cb60c0a2d3cd458dd41db
+oid sha256:f720d721c792d0a9412a85ed8fc6e2eb685bfd50ae210c270b08af2ed177b79e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8e23e4b636e6d4cfbe5cdf1b076811f8e1f9d4c97603e891aee3c95c35c66b
+oid sha256:5a75dcc5ec09eada6641b366eac390a2a47e7ec4306b94cfdb718bc9a73ac9b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013206223432792704,
+  "epoch": 0.026412446865585408,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 75.565,
       "eval_steps_per_second": 75.565,
       "step": 20
+    },
+    {
+      "epoch": 0.013866534604432339,
+      "grad_norm": 361644.25,
+      "learning_rate": 0.00029893625775634835,
+      "loss": 97.0436,
+      "step": 21
+    },
+    {
+      "epoch": 0.014526845776071974,
+      "grad_norm": 1564964.125,
+      "learning_rate": 0.0002987343436093454,
+      "loss": 279.3873,
+      "step": 22
+    },
+    {
+      "epoch": 0.015187156947711609,
+      "grad_norm": 1539204.875,
+      "learning_rate": 0.00029851497482766547,
+      "loss": 668.731,
+      "step": 23
+    },
+    {
+      "epoch": 0.015847468119351244,
+      "grad_norm": 2246419.0,
+      "learning_rate": 0.00029827817715520773,
+      "loss": 758.2188,
+      "step": 24
+    },
+    {
+      "epoch": 0.01650777929099088,
+      "grad_norm": 2776799.5,
+      "learning_rate": 0.0002980239783812289,
+      "loss": 546.4688,
+      "step": 25
+    },
+    {
+      "epoch": 0.017168090462630514,
+      "grad_norm": 1617533.25,
+      "learning_rate": 0.0002977524083370822,
+      "loss": 422.7344,
+      "step": 26
+    },
+    {
+      "epoch": 0.01782840163427015,
+      "grad_norm": 450934.75,
+      "learning_rate": 0.00029746349889271645,
+      "loss": 339.3945,
+      "step": 27
+    },
+    {
+      "epoch": 0.018488712805909784,
+      "grad_norm": 2286499.5,
+      "learning_rate": 0.0002971572839529358,
+      "loss": 236.2812,
+      "step": 28
+    },
+    {
+      "epoch": 0.01914902397754942,
+      "grad_norm": 3999992.25,
+      "learning_rate": 0.00029683379945342125,
+      "loss": 159.8123,
+      "step": 29
+    },
+    {
+      "epoch": 0.019809335149189054,
+      "grad_norm": 308621.125,
+      "learning_rate": 0.000296493083356513,
+      "loss": 124.3508,
+      "step": 30
+    },
+    {
+      "epoch": 0.02046964632082869,
+      "grad_norm": 497120.59375,
+      "learning_rate": 0.00029613517564675565,
+      "loss": 138.8941,
+      "step": 31
+    },
+    {
+      "epoch": 0.021129957492468324,
+      "grad_norm": 99928.7890625,
+      "learning_rate": 0.0002957601183262058,
+      "loss": 151.8223,
+      "step": 32
+    },
+    {
+      "epoch": 0.02179026866410796,
+      "grad_norm": 405539.0625,
+      "learning_rate": 0.000295367955409503,
+      "loss": 1203.2074,
+      "step": 33
+    },
+    {
+      "epoch": 0.022450579835747594,
+      "grad_norm": 463994.21875,
+      "learning_rate": 0.00029495873291870436,
+      "loss": 1256.5367,
+      "step": 34
+    },
+    {
+      "epoch": 0.02311089100738723,
+      "grad_norm": 953879.5625,
+      "learning_rate": 0.0002945324988778834,
+      "loss": 938.6675,
+      "step": 35
+    },
+    {
+      "epoch": 0.023771202179026868,
+      "grad_norm": 178221.28125,
+      "learning_rate": 0.00029408930330749477,
+      "loss": 356.9532,
+      "step": 36
+    },
+    {
+      "epoch": 0.0244315133506665,
+      "grad_norm": 146182.625,
+      "learning_rate": 0.0002936291982185036,
+      "loss": 238.3703,
+      "step": 37
+    },
+    {
+      "epoch": 0.025091824522306138,
+      "grad_norm": 116065.7421875,
+      "learning_rate": 0.00029315223760628217,
+      "loss": 212.9555,
+      "step": 38
+    },
+    {
+      "epoch": 0.02575213569394577,
+      "grad_norm": 129193.03125,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 227.929,
+      "step": 39
+    },
+    {
+      "epoch": 0.026412446865585408,
+      "grad_norm": 152996.75,
+      "learning_rate": 0.00029214797567742035,
+      "loss": 220.4361,
+      "step": 40
+    },
+    {
+      "epoch": 0.026412446865585408,
+      "eval_loss": 16.9798526763916,
+      "eval_runtime": 6.5479,
+      "eval_samples_per_second": 75.597,
+      "eval_steps_per_second": 75.597,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 15771925217280.0,
+  "total_flos": 28561970823168.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null