Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9dfb9a273258a4da0cd0abf9c473733d64de15c9b436a4e310a7516992aadc
+oid sha256:834b3f1780c9fd89f6bfa5f319b65a6486e6af60221f901d7e860780ad39830b
 size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f604aecb41e9633c05e8dd317b656732e5079082b765a72f0a34dfa3c306d7d0
+oid sha256:6b8e5d8ebe593ce6ffea74db7aefd5f8a2df25512838f857c42fe859f241094e
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a2cf6f432c6ef4028563f06584b1577c26f344c8073d1e42dc72f657ef2033
+oid sha256:77c94379f004ea0bd3b6c24318506613489998b98c0479ee6ca058b4723d9413
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb57dbd8526d420080443a568b84c7a184bdfc060adbe06867b56eb2f70fa448
+oid sha256:ea74371489dafdb6947d1051749433c783541685907f59e03a46eb374dc6453a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.102945354673738,
-  "global_step": 300000,
+  "epoch": 7.339710199829529,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3852,11 +3852,139 @@
       "eval_samples_per_second": 166.395,
       "eval_steps_per_second": 20.804,
       "step": 300000
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 1.1886226599741138e-06,
+      "loss": 2.4182,
+      "step": 300500
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 1.1254853679325695e-06,
+      "loss": 2.4228,
+      "step": 301000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.062348075891025e-06,
+      "loss": 2.4385,
+      "step": 301500
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 9.992107838494808e-07,
+      "loss": 2.4361,
+      "step": 302000
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 9.360734918079364e-07,
+      "loss": 2.43,
+      "step": 302500
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 8.729361997663921e-07,
+      "loss": 2.4245,
+      "step": 303000
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 8.097989077248477e-07,
+      "loss": 2.4383,
+      "step": 303500
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 7.466616156833035e-07,
+      "loss": 2.4207,
+      "step": 304000
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 6.835243236417591e-07,
+      "loss": 2.4286,
+      "step": 304500
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 6.203870316002147e-07,
+      "loss": 2.4143,
+      "step": 305000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 5.572497395586704e-07,
+      "loss": 2.4354,
+      "step": 305500
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 4.94112447517126e-07,
+      "loss": 2.4345,
+      "step": 306000
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 4.309751554755817e-07,
+      "loss": 2.4294,
+      "step": 306500
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 3.678378634340374e-07,
+      "loss": 2.4442,
+      "step": 307000
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 3.04700571392493e-07,
+      "loss": 2.4416,
+      "step": 307500
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 2.4156327935094866e-07,
+      "loss": 2.4323,
+      "step": 308000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 1.7842598730940432e-07,
+      "loss": 2.4233,
+      "step": 308500
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 1.1528869526785997e-07,
+      "loss": 2.4391,
+      "step": 309000
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 5.2151403226315624e-08,
+      "loss": 2.442,
+      "step": 309500
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 0.0,
+      "loss": 2.4491,
+      "step": 310000
+    },
+    {
+      "epoch": 7.34,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.8215,
+      "eval_samples_per_second": 166.387,
+      "eval_steps_per_second": 20.803,
+      "step": 310000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 6.3395167319424e+16,
+  "total_flos": 6.5501895567744e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f604aecb41e9633c05e8dd317b656732e5079082b765a72f0a34dfa3c306d7d0
+oid sha256:6b8e5d8ebe593ce6ffea74db7aefd5f8a2df25512838f857c42fe859f241094e
 size 510398013