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:f2ab2a355213f1f5bf0a9bc2d7411c24cbbf64711ffef3a29f1c274960250373
+oid sha256:794bed3415be79d8a164a34b2d4810fc31fc907565dbded7aefdea8663335e3f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e59c07c58546c4ea771888a4dcb5371ee003a63e19806bcdb8a01c6381ba410
+oid sha256:3d9a2b8bea77598f49595ebb8d3e9bf3c0bb9206e61bfe244fe61650bb9e87c6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d841eda044e2a0b4625c1a49f398ba41b30f358c4216b4153690415e794a13
+oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
 size 14244

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": 0.15015015015015015,
+  "epoch": 0.22522522522522523,
   "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": 1.2276,
       "step": 50
+    },
+    {
+      "epoch": 0.15315315315315314,
+      "grad_norm": 0.6700219511985779,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.1085,
+      "step": 51
+    },
+    {
+      "epoch": 0.15615615615615616,
+      "grad_norm": 0.70674067735672,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.0032,
+      "step": 52
+    },
+    {
+      "epoch": 0.15915915915915915,
+      "grad_norm": 0.6413066387176514,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.0976,
+      "step": 53
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.5945645570755005,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.0874,
+      "step": 54
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "eval_loss": 1.1248000860214233,
+      "eval_runtime": 62.8374,
+      "eval_samples_per_second": 4.472,
+      "eval_steps_per_second": 0.573,
+      "step": 54
+    },
+    {
+      "epoch": 0.16516516516516516,
+      "grad_norm": 0.5928006172180176,
+      "learning_rate": 5e-05,
+      "loss": 1.1226,
+      "step": 55
+    },
+    {
+      "epoch": 0.16816816816816818,
+      "grad_norm": 0.5897536277770996,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.061,
+      "step": 56
+    },
+    {
+      "epoch": 0.17117117117117117,
+      "grad_norm": 0.6264550089836121,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0425,
+      "step": 57
+    },
+    {
+      "epoch": 0.17417417417417416,
+      "grad_norm": 0.5464336276054382,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.0925,
+      "step": 58
+    },
+    {
+      "epoch": 0.17717717717717718,
+      "grad_norm": 0.5804792642593384,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.1799,
+      "step": 59
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.6067994832992554,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.0761,
+      "step": 60
+    },
+    {
+      "epoch": 0.1831831831831832,
+      "grad_norm": 0.5299519896507263,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.0996,
+      "step": 61
+    },
+    {
+      "epoch": 0.18618618618618618,
+      "grad_norm": 0.7131068706512451,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.0971,
+      "step": 62
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 0.5988982915878296,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.0842,
+      "step": 63
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "eval_loss": 1.098732352256775,
+      "eval_runtime": 62.8005,
+      "eval_samples_per_second": 4.474,
+      "eval_steps_per_second": 0.573,
+      "step": 63
+    },
+    {
+      "epoch": 0.1921921921921922,
+      "grad_norm": 0.7022519111633301,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.046,
+      "step": 64
+    },
+    {
+      "epoch": 0.19519519519519518,
+      "grad_norm": 0.5209968686103821,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.013,
+      "step": 65
+    },
+    {
+      "epoch": 0.1981981981981982,
+      "grad_norm": 0.6534311771392822,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.0596,
+      "step": 66
+    },
+    {
+      "epoch": 0.2012012012012012,
+      "grad_norm": 0.6855350136756897,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.1311,
+      "step": 67
+    },
+    {
+      "epoch": 0.2042042042042042,
+      "grad_norm": 0.5221145749092102,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.0387,
+      "step": 68
+    },
+    {
+      "epoch": 0.2072072072072072,
+      "grad_norm": 0.48642462491989136,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.0218,
+      "step": 69
+    },
+    {
+      "epoch": 0.21021021021021022,
+      "grad_norm": 0.6832244396209717,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9763,
+      "step": 70
+    },
+    {
+      "epoch": 0.2132132132132132,
+      "grad_norm": 0.5838537812232971,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.0369,
+      "step": 71
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.579451322555542,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.9797,
+      "step": 72
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "eval_loss": 1.0829377174377441,
+      "eval_runtime": 63.4887,
+      "eval_samples_per_second": 4.426,
+      "eval_steps_per_second": 0.567,
+      "step": 72
+    },
+    {
+      "epoch": 0.21921921921921922,
+      "grad_norm": 0.688620924949646,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.0522,
+      "step": 73
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.5413029193878174,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0064,
+      "step": 74
+    },
+    {
+      "epoch": 0.22522522522522523,
+      "grad_norm": 0.5388117432594299,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.0725,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.41887283560448e+16,
+  "total_flos": 1.112830925340672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null