Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516c21f3c47b84533cbd3586f53cbf75d328f3d9b925ae50f1d9592ff33e5112
+oid sha256:b383fa90f7293897c37b40f067f202019bba2c3453db8d1f328f6d7383cad678
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dba20d470df9ae93e558c67d830203c69e1e8b73fcbce7e80720bf64c0125dd
+oid sha256:485ed4a755afcfc6deaa5749cdb0f525c637fe083bc46abe1fbf43c5b6a8379e
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
+oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
+oid sha256:8ff31836ff2c96f7fb19d95df664b507273477e3a4f87dcce611b28b7e31820b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7839849125847391,
-  "global_step": 70000,
+  "epoch": 2.038839900096845,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1406,11 +1406,211 @@
       "eval_samples_per_second": 804.488,
       "eval_steps_per_second": 12.872,
       "step": 70000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0002934838153624519,
+      "loss": 0.3243,
+      "step": 70500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00029334092796560427,
+      "loss": 0.3238,
+      "step": 71000
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.8432244658470154,
+      "eval_runtime": 1.2842,
+      "eval_samples_per_second": 778.669,
+      "eval_steps_per_second": 12.459,
+      "step": 71000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002931965276945326,
+      "loss": 0.3235,
+      "step": 71500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0002930506161283751,
+      "loss": 0.3235,
+      "step": 72000
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.8572074174880981,
+      "eval_runtime": 1.2536,
+      "eval_samples_per_second": 797.713,
+      "eval_steps_per_second": 12.763,
+      "step": 72000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00029290319486279724,
+      "loss": 0.3229,
+      "step": 72500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0002927542655099744,
+      "loss": 0.3227,
+      "step": 73000
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.8465535044670105,
+      "eval_runtime": 1.184,
+      "eval_samples_per_second": 844.583,
+      "eval_steps_per_second": 13.513,
+      "step": 73000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00029260382969857417,
+      "loss": 0.3223,
+      "step": 73500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00029245188907373845,
+      "loss": 0.3224,
+      "step": 74000
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.8523721694946289,
+      "eval_runtime": 1.247,
+      "eval_samples_per_second": 801.902,
+      "eval_steps_per_second": 12.83,
+      "step": 74000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002922984452970655,
+      "loss": 0.3219,
+      "step": 74500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.000292143500046592,
+      "loss": 0.3217,
+      "step": 75000
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.8451367616653442,
+      "eval_runtime": 1.266,
+      "eval_samples_per_second": 789.893,
+      "eval_steps_per_second": 12.638,
+      "step": 75000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0002919870550167743,
+      "loss": 0.3216,
+      "step": 75500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0002918291119184702,
+      "loss": 0.321,
+      "step": 76000
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.8452543020248413,
+      "eval_runtime": 1.2406,
+      "eval_samples_per_second": 806.062,
+      "eval_steps_per_second": 12.897,
+      "step": 76000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002916696724789201,
+      "loss": 0.321,
+      "step": 76500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00029150873844172823,
+      "loss": 0.3207,
+      "step": 77000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.8388876914978027,
+      "eval_runtime": 1.2429,
+      "eval_samples_per_second": 804.592,
+      "eval_steps_per_second": 12.873,
+      "step": 77000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00029134631156684334,
+      "loss": 0.3204,
+      "step": 77500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0002911823936305398,
+      "loss": 0.3202,
+      "step": 78000
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 0.8390601873397827,
+      "eval_runtime": 1.2051,
+      "eval_samples_per_second": 829.802,
+      "eval_steps_per_second": 13.277,
+      "step": 78000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002910169864253979,
+      "loss": 0.3198,
+      "step": 78500
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0002908500917602842,
+      "loss": 0.3195,
+      "step": 79000
+    },
+    {
+      "epoch": 2.01,
+      "eval_loss": 0.853469729423523,
+      "eval_runtime": 1.2478,
+      "eval_samples_per_second": 801.439,
+      "eval_steps_per_second": 12.823,
+      "step": 79000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00029068171146033226,
+      "loss": 0.3196,
+      "step": 79500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002905118473669218,
+      "loss": 0.3194,
+      "step": 80000
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 0.8577731847763062,
+      "eval_runtime": 1.1943,
+      "eval_samples_per_second": 837.345,
+      "eval_steps_per_second": 13.398,
+      "step": 80000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 2.236396492508455e+21,
+  "total_flos": 2.55587015236991e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dba20d470df9ae93e558c67d830203c69e1e8b73fcbce7e80720bf64c0125dd
+oid sha256:485ed4a755afcfc6deaa5749cdb0f525c637fe083bc46abe1fbf43c5b6a8379e
 size 102501541