Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fea028c5bfc9404f2b619405e732a8bae394cb83febbe5f12b63d0e52dfeb6
-size 202193937
+oid sha256:516c21f3c47b84533cbd3586f53cbf75d328f3d9b925ae50f1d9592ff33e5112
+size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c3180802a5713b7e9f66986161446bd671e1f39c69b59568ccc20114bb8c6
+oid sha256:8dba20d470df9ae93e558c67d830203c69e1e8b73fcbce7e80720bf64c0125dd
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
+oid sha256:27edff49d78e2d5201b5045fee88ae8b7f202be6590fb23f8ba498906050d4bc
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
+oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5291299250726338,
-  "global_step": 60000,
+  "epoch": 1.7839849125847391,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1206,11 +1206,211 @@
       "eval_samples_per_second": 752.666,
       "eval_steps_per_second": 12.043,
       "step": 60000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00029602157489814693,
+      "loss": 0.3311,
+      "step": 60500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00029590925100598365,
+      "loss": 0.3307,
+      "step": 61000
+    },
+    {
+      "epoch": 1.55,
+      "eval_loss": 0.8626954555511475,
+      "eval_runtime": 1.268,
+      "eval_samples_per_second": 788.647,
+      "eval_steps_per_second": 12.618,
+      "step": 61000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.000295795386152827,
+      "loss": 0.3302,
+      "step": 61500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0002956799815838848,
+      "loss": 0.3298,
+      "step": 62000
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.8434558510780334,
+      "eval_runtime": 1.2564,
+      "eval_samples_per_second": 795.92,
+      "eval_steps_per_second": 12.735,
+      "step": 62000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002955630385612029,
+      "loss": 0.3294,
+      "step": 62500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002954445583636515,
+      "loss": 0.3292,
+      "step": 63000
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.8569065928459167,
+      "eval_runtime": 1.2969,
+      "eval_samples_per_second": 771.061,
+      "eval_steps_per_second": 12.337,
+      "step": 63000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029532454228691103,
+      "loss": 0.3288,
+      "step": 63500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002952029916434581,
+      "loss": 0.3287,
+      "step": 64000
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 0.8517204523086548,
+      "eval_runtime": 1.2275,
+      "eval_samples_per_second": 814.648,
+      "eval_steps_per_second": 13.034,
+      "step": 64000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00029507990776255107,
+      "loss": 0.3282,
+      "step": 64500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00029495529199021555,
+      "loss": 0.3278,
+      "step": 65000
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 0.8487727046012878,
+      "eval_runtime": 1.2356,
+      "eval_samples_per_second": 809.327,
+      "eval_steps_per_second": 12.949,
+      "step": 65000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0002948291456892296,
+      "loss": 0.3273,
+      "step": 65500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00029470147023910907,
+      "loss": 0.3269,
+      "step": 66000
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.8469608426094055,
+      "eval_runtime": 1.2425,
+      "eval_samples_per_second": 804.832,
+      "eval_steps_per_second": 12.877,
+      "step": 66000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002945722670360921,
+      "loss": 0.3265,
+      "step": 66500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0002944415374931243,
+      "loss": 0.3262,
+      "step": 67000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.8486921191215515,
+      "eval_runtime": 1.2218,
+      "eval_samples_per_second": 818.455,
+      "eval_steps_per_second": 13.095,
+      "step": 67000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00029430928303984295,
+      "loss": 0.326,
+      "step": 67500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002941755051225616,
+      "loss": 0.3257,
+      "step": 68000
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 0.8429991602897644,
+      "eval_runtime": 1.2262,
+      "eval_samples_per_second": 815.556,
+      "eval_steps_per_second": 13.049,
+      "step": 68000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00029404020520425417,
+      "loss": 0.3253,
+      "step": 68500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002939033847645388,
+      "loss": 0.325,
+      "step": 69000
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.8381994366645813,
+      "eval_runtime": 1.2665,
+      "eval_samples_per_second": 789.582,
+      "eval_steps_per_second": 12.633,
+      "step": 69000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00029376504529966195,
+      "loss": 0.3246,
+      "step": 69500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00029362518832248184,
+      "loss": 0.3248,
+      "step": 70000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.848027229309082,
+      "eval_runtime": 1.243,
+      "eval_samples_per_second": 804.488,
+      "eval_steps_per_second": 12.872,
+      "step": 70000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.916909353733955e+21,
+  "total_flos": 2.236396492508455e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c3180802a5713b7e9f66986161446bd671e1f39c69b59568ccc20114bb8c6
+oid sha256:8dba20d470df9ae93e558c67d830203c69e1e8b73fcbce7e80720bf64c0125dd
 size 102501541