Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca6b069f65aa61429387188b368c55cdc14261221c22bea5b90acd29ed3f1d40
+oid sha256:5f8f916144b97d4ddaaa68594ce549a3d0aad2914b41bcaaf1ec89b0fa386bd5
 size 37134420

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad70bae417fea217f6030e746ac1a46c6b1f642874878654cb2b0a9313d3c2cb
+oid sha256:05c201bc495760ecf81e3a8aac05f9bd362b48b7014ed6b59128128b4804cbe6
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed97e4effc8cc706427ccc73b0048401e6016e71f210e07c43ef20b1160a27d
+oid sha256:2e796d3abe6e9bbe48f5638e33ea6d9f90f3f55e92595c8e35f58bacd11f4124
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01dd1ef3dff59a46ab95cae98f72234ae45e0225057ea2382d1d6a0cf11647a
+oid sha256:b8aa786061f7c99f6db00dcfd8675d7ade5c75f02b1f2bd445ff74fdc042c6de
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e241b2a00c7d1568e69b70492eede367aea70326bde0c8d4c6df4e686d4eff8
+oid sha256:6ad7f7e7b759afa79724c3ad270dd1c777cff625092f285c5bd7cf06f792831c
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbba45eec4e431103e03115cf1abb0fbb9ba54a601065a6e91d6025886821eb
+oid sha256:a808d1867f13d448b79e0f402afc708c7b249b39c403692d66be72b76d2d4589
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbe4132bcc02cbe35ae58586fa18777ccc4a6874318646a1956c9364ae8dfd8
+oid sha256:0fbdba7e06e397a97fc796a6bb07243aee073f36afac35c847cf01b85e0af29d
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35e8ce36b6d9a33913a1b929a57f56cf5e18239f6a5bdb3300b0e44b01678c5
+oid sha256:1470bd4d59e6239f849257c72c690f54f661d542c4aa74cc6380ca38025758f3
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57b44cb0f4c1d4f6fb310f448131297bb8aa17e47d1d8d82299f9cac85e7810
+oid sha256:29aea3631f2553b0a44f1b1251a4fceab067cc6c7873b6857f6e1f8fecd0042e
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1423487544483986,
+  "epoch": 0.21352313167259787,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 37.51,
       "eval_steps_per_second": 4.748,
       "step": 10
+    },
+    {
+      "epoch": 0.15658362989323843,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2346.3477,
+      "step": 11
+    },
+    {
+      "epoch": 0.1708185053380783,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 362.8186,
+      "step": 12
+    },
+    {
+      "epoch": 0.18505338078291814,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2926.6011,
+      "step": 13
+    },
+    {
+      "epoch": 0.199288256227758,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 595.2302,
+      "step": 14
+    },
+    {
+      "epoch": 0.21352313167259787,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 591.5734,
+      "step": 15
+    },
+    {
+      "epoch": 0.21352313167259787,
+      "eval_loss": NaN,
+      "eval_runtime": 12.5898,
+      "eval_samples_per_second": 37.649,
+      "eval_steps_per_second": 4.766,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.123764987625472e+16,
+  "total_flos": 7.685647481438208e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null