Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "gate_proj",
     "down_proj",
+    "v_proj",
     "q_proj",
     "k_proj",
-    "v_proj",
-    "gate_proj",
+    "o_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:599547c7872fadb3e881464e4a020f2116fc88c5b3188af8b5411670dd295a7c
+oid sha256:4a221136dbd7c845c6c0c1550e77be0de60812d4d279b8dc7ce7a58800c49e9c
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d0b4da74aa12381baffc346fe8c94467a7f3cec3ea54671920f25923ab57f0
+oid sha256:45663c9877b6e891d5df26606662cb699528ca87d2351c211a10529b55c9a87a
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b24fc1ce0ebd43a5a2c02d4cd0e240082f722605ae31afde9e2954adcd4790
+oid sha256:011d57303a75fb8a2e485a8073e0f691c69b7d80a9f1120b703e475e9e6035b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005638037962788949,
+  "epoch": 0.001691411388836685,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00018793459875963165,
-      "grad_norm": 0.4121508002281189,
+      "grad_norm": 0.41265636682510376,
       "learning_rate": 2e-05,
       "loss": 2.0097,
       "step": 1
@@ -18,32 +18,90 @@
     {
       "epoch": 0.00018793459875963165,
       "eval_loss": 2.225860595703125,
-      "eval_runtime": 104.6968,
-      "eval_samples_per_second": 10.707,
-      "eval_steps_per_second": 10.707,
+      "eval_runtime": 59.1454,
+      "eval_samples_per_second": 18.953,
+      "eval_steps_per_second": 18.953,
       "step": 1
     },
     {
       "epoch": 0.0003758691975192633,
-      "grad_norm": 0.34095901250839233,
+      "grad_norm": 0.34109458327293396,
       "learning_rate": 4e-05,
       "loss": 2.0424,
       "step": 2
     },
     {
       "epoch": 0.0005638037962788949,
-      "grad_norm": 0.4388081431388855,
+      "grad_norm": 0.4408990442752838,
       "learning_rate": 6e-05,
       "loss": 2.2435,
       "step": 3
     },
     {
       "epoch": 0.0005638037962788949,
-      "eval_loss": 2.2231271266937256,
-      "eval_runtime": 105.4847,
-      "eval_samples_per_second": 10.627,
-      "eval_steps_per_second": 10.627,
+      "eval_loss": 2.2232234477996826,
+      "eval_runtime": 53.5686,
+      "eval_samples_per_second": 20.926,
+      "eval_steps_per_second": 20.926,
       "step": 3
+    },
+    {
+      "epoch": 0.0007517383950385266,
+      "grad_norm": 0.3058125972747803,
+      "learning_rate": 8e-05,
+      "loss": 2.1183,
+      "step": 4
+    },
+    {
+      "epoch": 0.0009396729937981583,
+      "grad_norm": 0.44318097829818726,
+      "learning_rate": 0.0001,
+      "loss": 2.2092,
+      "step": 5
+    },
+    {
+      "epoch": 0.0011276075925577898,
+      "grad_norm": 0.3183535933494568,
+      "learning_rate": 0.00012,
+      "loss": 2.2227,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011276075925577898,
+      "eval_loss": 2.2024617195129395,
+      "eval_runtime": 54.1467,
+      "eval_samples_per_second": 20.703,
+      "eval_steps_per_second": 20.703,
+      "step": 6
+    },
+    {
+      "epoch": 0.0013155421913174216,
+      "grad_norm": 0.4959358274936676,
+      "learning_rate": 0.00014,
+      "loss": 2.1984,
+      "step": 7
+    },
+    {
+      "epoch": 0.0015034767900770532,
+      "grad_norm": 0.3904803693294525,
+      "learning_rate": 0.00016,
+      "loss": 2.1435,
+      "step": 8
+    },
+    {
+      "epoch": 0.001691411388836685,
+      "grad_norm": 0.3693416714668274,
+      "learning_rate": 0.00018,
+      "loss": 2.0586,
+      "step": 9
+    },
+    {
+      "epoch": 0.001691411388836685,
+      "eval_loss": 2.149339437484741,
+      "eval_runtime": 52.9676,
+      "eval_samples_per_second": 21.164,
+      "eval_steps_per_second": 21.164,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 208716913704960.0,
+  "total_flos": 626150741114880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb88f4cc1adc89d4050bb1bb8aee4d5e2999228bec3f38fcda07d103361cace
+oid sha256:66aba1548284fb45544c3c449ae78c0d06cde4d353a7cacc54939951423f8e9a
 size 6776