Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed3bfef55fffb18b388c9e1137f490b938699bc48b9dc01747bdcad7f0171be
+oid sha256:5d1dfb33f6ccaf0aa041c684f44a5d0ee62d14199d79f04977db1cbf8b26adca
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f0f9f4573c5adca20e05cda02e58de06c410369aa689e8c1299006186e463e
+oid sha256:ec16ae559f8cebe5e891e4ae16ecabaff490ae1579f7e11b309961929e27c27c
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab6ab31eba3f3f590a5cfc6be92ff1e19f4cacc4d0fe05b84acd59f0b8005da
+oid sha256:a847f6d574b0dda7a227928235d35e1e309cf64d716022f1bf07b0d72e340a31
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed73a93f3f0252767129271fcda6cff59a3916854d06e67c512a0f1f221095a0
+oid sha256:8100b959b78283c55a935b227ffa211cda0e53f65f4961c2d6c0667c389b9630
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd0b478b7542fadf1ead0e87d169c93ae06220f14aa882c5d1c0749fac62b93
+oid sha256:8a02738c82d8e0edc7cf93ff13106fd4a257bf7abf4ad28d740dfe5352665b22
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb33054efd224874144ea3d764ced3dce953ed61e0f8e47392a2a9fb6bdacb1
+oid sha256:aa6b5ae6474e83494ba11d896561401459b7ed194dc0416ad9c1dada0113c0cf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1494252873563218,
+  "epoch": 1.7241379310344827,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 2.9765,
       "step": 50
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 4.141868591308594,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 3.597,
+      "step": 51
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 1.9662575721740723,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.136,
+      "step": 52
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 1.9346809387207031,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.8733,
+      "step": 53
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 5.7119364738464355,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.6832,
+      "step": 54
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "eval_loss": 3.386746644973755,
+      "eval_runtime": 2.1621,
+      "eval_samples_per_second": 67.528,
+      "eval_steps_per_second": 2.313,
+      "step": 54
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 7.614490985870361,
+      "learning_rate": 5e-05,
+      "loss": 3.3329,
+      "step": 55
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 8.576265335083008,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.1484,
+      "step": 56
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 2.174159049987793,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.041,
+      "step": 57
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.6589335203170776,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.3295,
+      "step": 58
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 5.215062141418457,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 3.2889,
+      "step": 59
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 2.2243685722351074,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.2102,
+      "step": 60
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 6.214241981506348,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 3.3818,
+      "step": 61
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 6.380526542663574,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.3575,
+      "step": 62
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 4.525617599487305,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.2245,
+      "step": 63
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "eval_loss": 3.2319209575653076,
+      "eval_runtime": 2.1603,
+      "eval_samples_per_second": 67.582,
+      "eval_steps_per_second": 2.314,
+      "step": 63
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 1.7523378133773804,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.2592,
+      "step": 64
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 3.5593461990356445,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.1112,
+      "step": 65
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 3.8328521251678467,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.354,
+      "step": 66
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 2.212510824203491,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 3.2925,
+      "step": 67
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 2.8463003635406494,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.0859,
+      "step": 68
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 2.9076786041259766,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.1054,
+      "step": 69
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 2.6354947090148926,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.1639,
+      "step": 70
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 1.233817219734192,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 3.1697,
+      "step": 71
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 3.946552038192749,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.3657,
+      "step": 72
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "eval_loss": 3.222416400909424,
+      "eval_runtime": 2.1573,
+      "eval_samples_per_second": 67.678,
+      "eval_steps_per_second": 2.318,
+      "step": 72
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 3.0761539936065674,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.1671,
+      "step": 73
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 1.3344730138778687,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.1811,
+      "step": 74
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 4.6756062507629395,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.2284,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.483774567120896e+17,
+  "total_flos": 2.225661850681344e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null